Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2869 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0755. Min Range: -9.0755
Max Act: 9.0755. Min Act: -0.1700
Data Index: 6324209 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0755. Min Range: -9.0755
Max Act: 9.0755. Min Act: -0.1700
Data Index: 3393902 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0755. Min Range: -9.0755
Max Act: 9.0130. Min Act: -0.1700
Data Index: 1750613 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.8255. Min Act: -0.1700
Data Index: 6108138 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.8255. Min Act: -0.1700
Data Index: 2918974 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.7630. Min Act: -0.1700
Data Index: 7069919 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.7005. Min Act: -0.1700
Data Index: 7589579 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.6380. Min Act: -0.1700
Data Index: 7671253 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.6380. Min Act: -0.1700
Data Index: 1858182 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.6380. Min Act: -0.1700
Data Index: 5454296 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.5130. Min Act: -0.1700
Data Index: 7362964 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.4505. Min Act: -0.1700
Data Index: 4871068 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.4505. Min Act: -0.1700
Data Index: 6633226 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.4505. Min Act: -0.1700
Data Index: 4872334 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.4505. Min Act: -0.1700
Data Index: 996088 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.4505. Min Act: -0.1700
Data Index: 1135660 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.4505. Min Act: -0.1700
Data Index: 5086918 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.3880. Min Act: -0.1700
Data Index: 5923839 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.3880. Min Act: -0.1700
Data Index: 549702 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0755. Min Range: -9.0755
Max Act: 8.3880. Min Act: -0.1700
Data Index: 6284337 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19